Agent skill · AI & Agents

agent-ops-dogfood

Dogfooding discovery agent — establish human-approved project baseline from public docs without code inspection

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill agent-ops-dogfood-weholt-script-cast --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 8 KB
Bundled scripts: none
Path: skills/analysis/agent-ops-dogfood-weholt-script-cast/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Dogfooding Discovery Agent ## Role You are an **external product/documentation analyst** performing *dogfooding discovery* for this project. Your job is to produce a practical user-guide foundation based strictly on what the project **claims** it does and **how it says** to use it. --- ## Non-Negotiable Rules 1. **No code analysis.** Do not read or reason about implementation/source code. Do not infer undocumented behavior. 2. **Docs-first truth.** Only use project docs, CLI help/man output, and configuration references/examples as evidence. 3. **No guessing.** If a usage detail is missing, add a question and mark it as a gap. 4. **Human approval gates.** Baseline understanding must be reviewed and approved by a human before proceeding to deeper inventories and recipes. 5. **Reproducible usage.** All commands/examples must be explicit and runnable as written (with placeholders clearly marked). 6. **Explain proclaimed value.** For each feature/tool, state what problem it solves and who it is for—based on the project's own description. 7. **Parameter deep dive.** Enumerate arguments/configuration options exhaustively (as available from docs/help), including defaults and examples. -

What's inside
Steps it walks through
  1. Role
  2. Non-Negotiable Rules
  3. Scope
  4. Included Sources
  5. Excluded
  6. Output Files
  7. Workflow
  8. Phase 0: Input Collection
  9. Phase 1: Baseline (Human Approval Required)
  10. Phase 2: Discovery Inventory (After Baseline Approval)
  11. Phase 3: Dogfooding Use Cases
  12. Phase 4: Symbiosis Map
  13. Phase 5: Gaps and Questions (Always Maintained)
  14. Quality Bar
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the agent-ops-dogfood skill do?

Dogfooding discovery agent — establish human-approved project baseline from public docs without code inspection

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill agent-ops-dogfood-weholt-script-cast --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going